Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to communication and exchange of messages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "correspond" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uv
    -0.73
    EGA
    -0.67
    dfx
    -0.66
    steen
    -0.65
    oufl
    -0.65
    ghazi
    -0.63
    asts
    -0.63
    selection
    -0.61
     heel
    -0.60
    GPU
    -0.60
    POSITIVE LOGITS
    ences
    1.16
    ingly
    1.10
    hip
    0.92
    hips
    0.91
    ents
    0.81
    entially
    0.81
    ioned
    0.81
    ing
    0.81
    ette
    0.80
    ificantly
    0.80
    Act Density 0.027%

    No Known Activations